{"total":211,"rows":[{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896,"area":null},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739,"area":null},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366,"area":null},{"id":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324,"area":null},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269,"area":null},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231,"area":null},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230,"area":null},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197,"area":null},{"id":"2211.04486","title":"Active Example Selection for In-Context Learning","created":"2022-11-08","cited_by_count":196,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173,"area":null},{"id":"2111.01998","title":"OpenPrompt: An Open-source Framework for Prompt-learning","created":"2021-11-03","cited_by_count":148,"area":null},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"area":null},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114,"area":null},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"area":null},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"area":null},{"id":"2312.11795","title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA","created":"2023-12-19","cited_by_count":80,"area":null},{"id":"2202.07962","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","created":"2022-02-16","cited_by_count":76,"area":null},{"id":"2111.06719","title":"On Transferability of Prompt Tuning for Natural Language Processing","created":"2021-11-12","cited_by_count":75,"area":null},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72,"area":null},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70,"area":null},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"area":null},{"id":"2305.03937","title":"Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization","created":"2023-05-06","cited_by_count":64,"area":null},{"id":"2305.07961","title":"Leveraging Large Language Models in Conversational Recommender Systems","created":"2023-05-13","cited_by_count":63,"area":null},{"id":"2205.12647","title":"Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation","created":"2022-05-25","cited_by_count":62,"area":null},{"id":"2306.04344","title":"ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation","created":"2023-06-07","cited_by_count":58,"area":null},{"id":"2212.03220","title":"Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning","created":"2022-12-06","cited_by_count":57,"area":null},{"id":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"id":"2505.14671","title":"UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens","created":"2025-05-20","cited_by_count":56,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"area":null},{"id":"2406.11675","title":"BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2211.12485","title":"HyperTuning: Toward Adapting Large Language Models without Back-propagation","created":"2022-11-22","cited_by_count":46,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2203.06654","title":"Continual Prompt Tuning for Dialog State Tracking","created":"2022-03-13","cited_by_count":44,"area":null},{"id":"2311.13534","title":"LM-Cocktail: Resilient Tuning of Language Models via Model Merging","created":"2023-11-22","cited_by_count":44,"area":null},{"id":"2310.19698","title":"When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations","created":"2023-10-30","cited_by_count":43,"area":null},{"id":"2405.17357","title":"DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution","created":"2024-05-27","cited_by_count":43,"area":null},{"id":"2210.05497","title":"Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models","created":"2022-10-11","cited_by_count":42,"area":null},{"id":"2304.14381","title":"$\\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation","created":"2023-04-27","cited_by_count":40,"area":null},{"id":"2312.10136","title":"Gradient-based Parameter Selection for Efficient Fine-Tuning","created":"2023-12-15","cited_by_count":40,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2211.10681","title":"Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning","created":"2022-11-19","cited_by_count":37,"area":null},{"id":"2310.05280","title":"Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems","created":"2023-10-08","cited_by_count":37,"area":null},{"id":"2309.05173","title":"DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning","created":"2023-09-11","cited_by_count":35,"area":null},{"id":"2204.10019","title":"Standing on the Shoulders of Giant Frozen Language Models","created":"2022-04-21","cited_by_count":33,"area":null},{"id":"2211.03831","title":"Multi-Head Adapter Routing for Cross-Task Generalization","created":"2022-11-07","cited_by_count":33,"area":null},{"id":"2312.05677","title":"Batched Low-Rank Adaptation of Foundation Models","created":"2023-12-09","cited_by_count":32,"area":null},{"id":"2210.04457","title":"XPrompt: Exploring the Extreme of Prompt Tuning","created":"2022-10-10","cited_by_count":30,"area":null},{"id":"2306.04933","title":"InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding","created":"2023-06-08","cited_by_count":30,"area":null},{"id":"2401.10545","title":"Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recency","created":"2024-01-19","cited_by_count":28,"area":null},{"id":"2305.10329","title":"G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2212.01853","title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","created":"2022-12-04","cited_by_count":24,"area":null},{"id":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23,"area":null},{"id":"2211.03154","title":"On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey","created":"2022-11-06","cited_by_count":23,"area":null},{"id":"2303.01580","title":"Mixture of Soft Prompts for Controllable Data Generation","created":"2023-03-02","cited_by_count":23,"area":null},{"id":"2305.01711","title":"Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner","created":"2023-05-02","cited_by_count":23,"area":null},{"id":"2310.05095","title":"How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts","created":"2023-10-08","cited_by_count":23,"area":null},{"id":"2205.01543","title":"Learning to Transfer Prompts for Text Generation","created":"2022-05-03","cited_by_count":22,"area":null},{"id":"2405.13952","title":"Spectral Adapter: Fine-Tuning in Spectral Space","created":"2024-05-22","cited_by_count":21,"area":null},{"id":"2409.13853","title":"Unlocking Memorization in Large Language Models with Dynamic Soft Prompting","created":"2024-09-20","cited_by_count":21,"area":null},{"id":"2409.06091","title":"Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity","created":"2024-09-09","cited_by_count":20,"area":null},{"id":"2305.13954","title":"Robust Prompt Optimization for Large Language Models Against Distribution Shifts","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2205.05313","title":"Towards Unified Prompt Tuning for Few-shot Text Classification","created":"2022-05-11","cited_by_count":18,"area":null},{"id":"2301.08771","title":"Matching Exemplar as Next Sentence Prediction (MeNSP): Zero-shot Prompt Learning for Automatic Scoring in Science Education","created":"2023-01-20","cited_by_count":18,"area":null},{"id":"2204.11117","title":"Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning","created":"2022-04-23","cited_by_count":17,"area":null},{"id":"2305.01239","title":"DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning","created":"2023-05-02","cited_by_count":17,"area":null},{"id":"2403.08370","title":"SMART: Submodular Data Mixture Strategy for Instruction Tuning","created":"2024-03-13","cited_by_count":17,"area":null},{"id":"2206.12131","title":"MVP: Multi-task Supervised Pre-training for Natural Language Generation","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2409.16434","title":"Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition","created":"2024-09-24","cited_by_count":16,"area":null},{"id":"2210.02952","title":"Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation","created":"2022-10-06","cited_by_count":15,"area":null},{"id":"2303.12314","title":"Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization","created":"2023-03-22","cited_by_count":15,"area":null},{"id":"2405.17484","title":"Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation","created":"2024-05-24","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2502.19980","title":"Can Textual Gradient Work in Federated Learning?","created":"2025-02-27","cited_by_count":15,"area":null},{"id":"2210.06277","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","created":"2022-10-12","cited_by_count":14,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2306.00618","title":"Effective Structured Prompting by Meta-Learning and Representative Verbalizer","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2312.01082","title":"A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness","created":"2023-12-02","cited_by_count":14,"area":null},{"id":"2408.00960","title":"PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting","created":"2024-08-02","cited_by_count":14,"area":null},{"id":"2302.06541","title":"Towards Agile Text Classifiers for Everyone","created":"2023-02-13","cited_by_count":13,"area":null},{"id":"2408.01119","title":"Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer","created":"2024-08-02","cited_by_count":13,"area":null},{"id":"2409.19458","title":"Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach","created":"2024-09-28","cited_by_count":13,"area":null},{"id":"2205.12604","title":"Leveraging QA Datasets to Improve Generative Data Augmentation","created":"2022-05-25","cited_by_count":12,"area":null},{"id":"2210.13712","title":"Parameter-Efficient Legal Domain Adaptation","created":"2022-10-25","cited_by_count":12,"area":null},{"id":"2303.02909","title":"Dynamic Prompting: A Unified Framework for Prompt Tuning","created":"2023-03-06","cited_by_count":12,"area":null},{"id":"2310.03331","title":"Fine-tune Language Models to Approximate Unbiased In-context Learning","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2310.14845","title":"ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2311.11686","title":"Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation","created":"2023-11-20","cited_by_count":12,"area":null},{"id":"2208.05577","title":"Reducing Retraining by Recycling Parameter-Efficient Prompts","created":"2022-08-10","cited_by_count":11,"area":null},{"id":"2210.07565","title":"Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning","created":"2022-10-14","cited_by_count":11,"area":null},{"id":"2301.10410","title":"One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER","created":"2023-01-25","cited_by_count":11,"area":null},{"id":"2302.08143","title":"Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2302.09236","title":"Scalable Prompt Generation for Semi-supervised Learning with Language Models","created":"2023-02-18","cited_by_count":11,"area":null}],"next_cursor":"100"}